INDEX

Explanations

duration and length

The neuron fires on numerical expressions specifying durations or time‐period lengths (e.g. terms, appointments, stays).

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

Negative Logits

-1.56

 There

-1.45

by

-1.40

豈

-1.37

no

-1.34

 tył

-1.31

 from

-1.31

 podczas

-1.30

 дает

-1.29

POSITIVE LOGITS

呖

1.54

ciled

1.50

錾

1.42

 唯美

1.41

Duration

1.38

ᅲ

1.38

]$}

1.37

 månader

1.36

鸛

1.36

 duration

1.35

Activations Density 0.145%